自动驾驶

VG4D: Vision-Language Model Goes 4D Video Recognition

Zhichao Deng, Xiangtai Li, Xia Li, Yunhai Tong, Shen Zhao, Mengyuan Liu

专题命中 激光雷达 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments ICRA 2024

3D Point Cloud Compression with Recurrent Neural Network and Image Compression Methods

Till Beemelmanns, Yuchen Tao, Bastian Lampe, Lennart Reiher, Raphael van Kempen, Timo Woopen, Lutz Eckstein

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.CV、eess.IV、cs.AI

Comments Code: https://github.com/ika-rwth-aachen/Point-Cloud-Compression

Journal ref 2022 IEEE Intelligent Vehicles Symposium (IV)

Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications

Shoki Ohta, Takayuki Nishio, Riichi Kudo, Kahoko Takahashi, Hisashi Nagata

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.CV、eess.IV、cs.AI

Journal ref IEEE Transactions on Machine Learning in Communications and Networking, vol. 1, pp. 258-276, 2023

EpiTESTER: Testing Autonomous Vehicles with Epigenetic Algorithm and Attention Mechanism

Chengjie Lu, Shaukat Ali, Tao Yue

专题命中 激光雷达 ：autonomous driving(abstract)；LiDAR(abstract)

Comments 17 pages, 8 figures, 2 tables

Vehicular Visible Light Positioning for Collision Avoidance and Platooning: A Survey

Burak Soner, Merve Karakas, Utku Noyan, Furkan Sahbaz, Sinem Coleri

专题命中 激光雷达 ：autonomous driving(abstract)；LiDAR(abstract)

Comments 17 pages, 13 figures

SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention

Efimia Panagiotaki, Daniele De Martini, Georgi Pramatarov, Matthew Gadd, Lars Kunze

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments International Conference on Advanced Robotics (ICAR 2023)

Orbital AI-based Autonomous Refuelling Solution

Duarte Rondao, Lei He, Nabil Aouf

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments 13 pages

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

Muhammad Ibrahim, Naveed Akhtar, Saeed Anwar, Michael Wise, Ajmal Mian

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Accepted in IEEE International Conference on Robotics and Automation (ICRA), 2023

Far3Det: Towards Far-Field 3D Detection

Shubham Gupta, Jeet Kanjani, Mengtian Li, Francesco Ferroni, James Hays, Deva Ramanan, Shu Kong

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments WACV 2023 12 Pages, 8 Figures, 10 Tables

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham

专题命中 激光雷达 ：occupancy(abstract)；分类 cs.RO、cs.CV、cs.AI

Lunar Rover Localization Using Craters as Landmarks

Larry Matthies, Shreyansh Daftry, Scott Tepsuporn, Yang Cheng, Deegan Atha, R. Michael Swan, Sanjna Ravichandar, Masahiro Ono

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments IEEE Aerospace Conference, 2022

Graph-Guided Deformation for Point Cloud Completion

Jieqi Shi, Lingyun Xu, Liang Heng, Shaojie Shen

专题命中 激光雷达 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments RAL with IROS 2021

SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition

Sourav Garg, Michael Milford

专题命中 激光雷达 ：autonomous driving(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Accepted to CVPR 2021 Workshop on 3D Vision and Robotics (3DVR). https://sites.google.com/view/cvpr2021-3d-vision-robotics/

Massively parallel coherent laser ranging using soliton microcombs

Johann Riemensberger, Anton Lukashchuk, Maxim Karpov, Wenle Weng, Erwan Lucas, Junqiu Liu, Tobias J. Kippenberg

专题命中 激光雷达 ：autonomous driving(abstract)；LiDAR(abstract)

Comments 18 pages, 12 Figures

Journal ref Nature 581, 164-170 (2020)

Hybrid Point Cloud Semantic Compression for Automotive Sensors: A Performance Evaluation

Andrea Varischio, Francesco Mandruzzato, Marcello Bullo, Marco Giordani, Paolo Testolina, Michele Zorzi

专题命中 激光雷达 ：autonomous driving(abstract)；LiDAR(abstract)

Comments 6 pages, 8 figures

Deep Parametric Continuous Convolutional Neural Networks

Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Accepted by CVPR 2018

Depth by Poking: Learning to Estimate Depth from Self-Supervised Grasping

Ben Goodrich, Alex Kuefler, William D. Richards

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、eess.IV

Comments IEEE International Conference on Robotics and Automation (ICRA) 2020

V2X-Based Vehicular Positioning: Opportunities, Challenges, and Future Directions

Seung-Woo Ko, Hyukjin Chae, Kaifeng Han, Seungmin Lee, Dong-Wook Seo, Kaibin Huang

专题命中 激光雷达 ：autonomous driving(abstract)；LiDAR(abstract)

Comments This work has been submitted to the IEEE for possible publication

Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network

Ali Jahani Amiri, Shing Yan Loo, Hong Zhang

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Submitted to IROS2019

RegNet: Multimodal Sensor Registration Using Deep Neural Networks

Nick Schneider, Florian Piewak, Christoph Stiller, Uwe Franke

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments published in IEEE Intelligent Vehicles Symposium, 2017

Rapid Debris-Volume Estimation from Post-Hurricane Aerial Imagery

飓风后航拍图像的快速 debris 体积估算

Kooshan Amini, Jamie Ellen Padgett, Guha Balakrishnan

机构 * Rice University（莱斯大学） ； Ken Kennedy Institute（肯·肯尼迪研究所） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.CV、eess.IV

AI总结 该研究提出 DebrisHeightNet 网络，利用飓风后单次航拍 RGB 图像，结合 CW-LMF 等技术实现残骸体积快速估算，精度优于传统参数化方法，部署便捷。

From crown candidates to neighborhood screening: integrating optical GeoAI and spatial modeling for urban-canopy assessment in Davis, California

从树冠候选到邻域筛选：整合光学地理人工智能与空间建模用于加利福尼亚州戴维斯市的城市树冠评估

Mohammadreza Narimani, Shreyan Mitra, Parastoo Farajpoor

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.CV、eess.IV

AI总结 本研究整合光学GeoAI与空间建模，利用2022年影像在戴维斯市生成树冠筛选层，绘制了该市9.37%的树冠，验证了其与热环境的关联，为城市规划提供支持。

Comments 17 pages, 10 figures + 5 supplementary figures, 7 tables. Preprint submitted to Taylor & Francis. Code: https://github.com/MohammadrezaNarimaniUCDavis/Davis_Urban_Canopy_GeoAI Data: https://doi.org/10.5281/zenodo.21925527

Unsupervised Point Cloud Registration with Self-Distillation

基于自蒸馏的无监督点云配准

Christian Löwens, Thorben Funke, André Wagner, Alexandru Paul Condurache

专题命中 激光雷达 ：autonomous driving(abstract)；分类 cs.RO、cs.CV

AI总结 本文针对点云配准依赖真实位姿标注的问题，提出自蒸馏无监督方法，在3DMatch基准上优于现有方法，且可泛化至汽车雷达场景。

Comments Oral at BMVC 2024

SLAM in Low-Light Environments: Project Report

低光照环境下的同步定位与地图构建：项目报告

Oleh Basystyi, Anna Stasyshyn, Oleksandr Kosovan, Yaroslav Prytula

机构 * Applied Sciences Faculty, Ukrainian Catholic University（乌克兰天主教大学应用科学学院） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 研究低光照环境下RGB相机的SLAM问题，对六种不同范式的系统在五个序列上进行基准测试，发现仅RGB的SLAM需惯性融合和全局优化才能稳定跟踪，为后续改进提供方向。

Comments Conducted as part of the certification program "Off-Road Visual Navigation: Development and Evaluation of Systems in Challenging Environments'' at the Faculty of Applied Sciences, Ukrainian Catholic University, in collaboration with the UCU UGV Club

Registering the 4D Millimeter Wave Radar Point Clouds Via Generalized Method of Moments

通过广义矩方法配准4D毫米波雷达点云

Xingyi Li, Han Zhang, Ziliang Wang, Yukai Yang, Weidong Chen

机构 * School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院） ； Institute of Medical Robotics, Shanghai Jiao Tong University（上海交通大学医疗机器人研究院） ； Department of Statistics, Uppsala University（乌普萨拉大学统计系） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 针对4D雷达点云稀疏噪声导致配准困难的问题，提出基于广义矩方法的配准框架，无需显式点对应，在合成与真实数据集上精度和鲁棒性优于基准方法，甚至接近激光雷达方法。

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

MM-Nav：基于多专家学习的多视角VLA模型用于鲁棒视觉导航

Tianyu Xu, Jiawei Chen, Jiazhao Zhang, Wenyao Zhang, Zekun Qi, Minghan Li, Zhizheng Zhang, He Wang

机构 * Peking University（北京大学） ； Galbot ； Shanghai Jiao Tong University（上海交通大学） ； Tsinghua University（清华大学） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 本文提出MM-Nav模型，通过多专家学习从合成数据中学习多样化的导航能力，展示模型在合成环境中的强泛化能力，并在现实世界实验中验证其有效性。

Comments Project page: https://pku-epic.github.io/MM-Nav-Web/

vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding

vS-Graphs: 通过分层场景理解紧密耦合视觉SLAM与3D场景图

Ali Tourani, Saad Ejaz, Hriday Bavle, Miguel Fernandez-Cortizas, David Morilla-Cabello, Jose Luis Sanchez-Lopez, Holger Voos

机构 * Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability, and Trust (SnT), University of Luxembourg（卢森堡大学自动化与机器人研究组，安全、可靠性与信任跨学科中心） ； Institute for Advanced Studies (IAS), University of Luxembourg（卢森堡大学高级研究院） ； Faculty of Science, Technology, and Medicine, University of Luxembourg（卢森堡大学科学、技术与医学学院） ； Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza（阿拉贡大学工程研究所（I3A）） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 本文提出vS-Graphs框架，通过结合视觉场景理解与地图重建，提升地图语义丰富度和可解释性，实验表明其在多个数据集上比现有方法提升15.22%的精度。

Comments 20 pages, 10 figures, 5 tables

On the Covariance of ICP-based Scan-matching Techniques

关于基于ICP的扫描匹配技术的协方差

Silvère Bonnabel, Martin Barczyk, François Goulette

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 本文研究了ICP算法计算旋转变换协方差的问题，指出点到点版本的ICP应用会导致错误协方差，通过数学证明验证点到平面版本的正确性。

Comments Accepted at 2016 American Control Conference

StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels

StruMPL：在不相交的部分监督和MNAR标签下的多任务密集回归

Reza M. Asiyabi, Juan Alberto Molina-Valero, The SEOSAW Partnership, Steven Hancock, Casey M. Ryan

机构 * School of Geosciences, University of Edinburgh, UK（爱丁堡大学地球科学学院，英国） ； National Centre for Earth Observation (NCEO), UK（英国地球观测国家中心） ； Department of Spatial Sciences, Faculty of Environmental Sciences Czech University of Life Sciences Prague, Praha, Czech Republic（环境科学学院空间科学系，捷克布拉格生命科学大学） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.CV、cs.AI

AI总结 本文针对在不相交的部分监督和MNAR标签下的多任务密集回归问题，提出StruMPL方法，通过共享编码器和可学习的物理模块，结合Augmented IPW损失函数，提高了对森林地上生物量的估计精度。

Comments 10 pages with 3 figures and 4 tables, References and Appendix 12 pages with 1 figure and 4 tables

When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning

当后门遇见部分可观测性：攻击现实世界的强化学习

Tairan Huang, Qingqing Ye, Yulin Jin, Jiawei Lian, Yaxin Xiao, Yi Wang, Haibo Hu

机构 * Department of Electrical and Electronic Engineering（电气与电子工程系） 纠错

专题命中 激光雷达 ：LiDAR(abstract)；分类 cs.RO、cs.CV

AI总结 本文提出DGBA框架，针对现实世界强化学习中部分可观测性问题，通过扩散引导后门攻击实现稳定攻击激活，实验表明其优于现有方法且不影响正常任务性能。